© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4148
    Prev
    Next
    INDEX
    Explanations

    eagerly awaiting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sWith
    -0.10
    tle
    -0.09
    rame
    -0.09
    sic
    -0.09
    ysis
    -0.09
    soever
    -0.08
    å¨ģåĬĽ
    -0.08
    tee
    -0.08
    gear
    -0.08
    uos
    -0.08
    POSITIVE LOGITS
     dÃłng
    0.11
    ingly
    0.11
    ä¸įå·²
    0.10
    ement
    0.10
    iously
    0.10
     má»ıi
    0.09
    å·²ä¹ħçļĦ
    0.09
    abin
    0.09
    æĹłæ¯Ķ
    0.09
     ÑģовÑģем
    0.09
    Activations Density 0.003%

    No Known Activations